Introduction to the Experiment
I’ve been publishing articles on Medium and occasionally sharing them on LinkedIn. Naturally, I wanted to know: Is all this writing actually causing people to follow me on LinkedIn? Or are my followers growing simply because I post on LinkedIn, regardless of whether there’s a Medium article involved? To find out, I designed a simple but powerful causal inference experiment.
The Challenge of Extracting Medium Statistics
Medium doesn’t make it easy for users to extract statistics relating to engagement and performance of their articles. These are the things I tried (and failed):
- Medium’s “Download your data” tool (only exports posts, not stats)
- Automated scrapers (Selenium, Playwright — blocked or invisible DOM)
- Intercepting network requests (GraphQL payloads hidden behind client-side rendering)
Manual Data Extraction
After a while of fruitless attempts at automation, I realized I was going to have to do this the much less satisfying way: a classic copy and paste job. Manually, I scrolled my Medium stats page and copy and pasted into a .txt file. I then parsed that file into structured data using a Python script.
Data Parsing with Python
I used the following Python script to parse the manually extracted data:
import pandas as pd
import re
text = open("medium_stats_raw.txt").read()
pattern = re.compile(r"(.*?)n([A-Za-z]{3,9} d{1,2}, d{4})n([d.,K]+)nViewsn([d.,K]+)nReadsn($[d.,]+|-)nEarnings")
def convert_k(val):
return int(float(val.replace('K','')) * 1000) if 'K' in val else int(val)Conclusion
Through this experiment, I aimed to understand the impact of publishing on Medium and sharing on LinkedIn on my follower growth. While the process of extracting data from Medium proved challenging and required manual effort, the insights gained from this causal inference experiment can provide valuable information for content creators looking to understand the effectiveness of their cross-platform posting strategies.
FAQs
- Q: Why is it hard to extract statistics from Medium?
- A: Medium does not provide a straightforward way to download or access detailed engagement statistics for articles, making data extraction challenging.
- Q: What was the purpose of the experiment?
- A: The experiment aimed to determine if publishing articles on Medium and sharing them on LinkedIn increases followers on LinkedIn.
- Q: How was the data from Medium extracted?
- A: Due to the lack of automated tools, the data was extracted manually through copy and paste, and then structured using a Python script.
